Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1556598 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.1992. Min Act: -0.0000

Data Index: 750201 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1540790 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0786. Min Act: -0.0000

Data Index: 526592 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1412070 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1424583 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1729200 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1377339 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1572592 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1369157 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9043. Min Act: -0.0000

Data Index: 556605 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9394. Min Act: -0.0000

Data Index: 503688 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9422. Min Act: -0.0000

Data Index: 241561 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0073. Min Act: -0.0000

Data Index: 337542 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9398. Min Act: -0.0000

Data Index: 563009 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9325. Min Act: -0.0000

Data Index: 395342 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1148592 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1067418 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1702019 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1448205 (The Pile)

Max Activating Token Index: 728